Open set domain adaptive image classification method and system

Abstract

The invention discloses an open set domain adaptive image classification method and system in the technical field of image recognition, and the method and system enable a network to better obtain domain invariant features through a channel attention mechanism, facilitate the migration of the features, and enable the features to be trained more easily. The method comprises the following steps: respectively inputting a labeled sample obtained from a source domain and an unlabeled sample obtained from a target domain into a feature extractor based on a channel attention module to obtain a weighted multi-channel feature map; sending the weighted multi-channel feature map into a label classifier, dividing samples with labels into K known categories, and dividing samples without labels into K known categories visible in a source domain and an unknown category invisible in the source domain; sending known categories from a source domain and a target domain to a domain discriminator, and enhancing domain invariant feature extraction based on the generative adversarial network; reducing inter-domain differences between the source domain and the target domain based on covariance matching.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to an open-set domain self-adaptive image classification method and system. Background technique [0002] In recent years, with the development of deep learning technology, computer vision has received extensive attention and made great progress. As a classic problem in computer vision, image classification is widely used in our daily production and life, such as medical image recognition, face recognition, license plate recognition, remote sensing image classification and so on. At present, traditional deep models are mainly obtained by learning a large amount of data in specific learning scenarios. However, to build such a good deep neural network often requires a large amount of labeled training data. It is difficult to obtain in some fields (such as medical images) where annotations are scarce and highly specialized. [0003] Closed-set domain adaptation...

AI Technical Summary

Problems solved by technology

There are also some problems, such as the source domain and target domain features are not fully aligned, training is easy to couple, etc.

In addition, there are problems such as long model training time and difficult convergence.

Images